NIST only participates in the February and August reviews.
We are developing machine learning algorithms to accelerate the discovery and optimization of advanced materials. These new algorithms form part of a research recommendation engine to guide researchers in the lab. The algorithms integrate machine learning, solid state physics, on-the-fly physical experiments, on-the-fly simulations, experiment and theory databases, and the theory of measurement instruments (e.g. X-ray diffractometers) to improve the ability to predict the results of future experiments.
We are primarily interested in guiding materials measurement experiments to acclerate learning the synthesis-process-structure-property relationship. Machine learning methods include, but are not limited to, Bayesian inference, constraint programming, Bayesian methods, sparse kernel machines, graphical models, and deep learning.
Some examples of materials classes of interest for this project are photovoltaic, thermoelectric, thermochromic, multiferroic, magnetic, and superconductive materials.
References
Liang, et al., 2025. Real-time experiment-theory closed-loop interaction for autonomous materials science. Science Advances, 11(27), p.eadu7426.
Kusne, et al., 2020. On-the-fly closed-loop materials discovery via Bayesian active learning. Nature communications, 11(1), p.5966.
Kusne, et al., 2024. Learning material synthesis–process–structure–property relationship by data fusion: Bayesian co-regionalization N-dimensional piecewise function learning. Digital Discovery, 3(11), pp.2211-2225.
Materials Genome Initiative; Machine learning; Combinatorial library; Informatics; High-throughput; Composition spread; Hyperspectral data Analysis; Data mining; Functional materials;